CoreCognition Image only Intentionality: leaderboard

CoreCognition Image only Intentionality — CoreCognition native component accuracy and reported mean. Image+Video, image-only and single-image populations are separate; no pooling or replacement across cohorts. Metric: Accuracy (%). Source: https://grow-ai-like-a-child.github.io/CoreCognition/leaderboard

Metric: Accuracy (%). Source: grow-ai-like-a-child.github.io. Saturation forecast: Rough model projection: around 2026. 77 models tracked. Updated 16 Nov 2026.

Top models

#ModelScoreOverall rank
1Step-1.5V-mini86.03#2720
2GLM-4V-Plus84.21#1400
3step-1o-turbo-vision83.1
4NVLM-D-72B81.11#2181
5Molmo-72B-092480.56#5272
6omchat79.76
7Cambrian-34B79.68#5295
8Ovis1.6-Gemma2-27B78.1#1833
9Bunny-Llama3-8B77.78#7560
10step-1v-32k77.06
11Cambrian-13B76.59#7053
12GLM-4V-9B76.51#3333
13parrot-14B76.51
14Reka Core76.35#3349
15points-qwen-2.5-7B-chat76.27

Interactive version: theaggregate.ai/benchmark?slug=corecognition-image-only-intentionality · How It Works · Data refreshed daily, snapshot 2026-11-16.